© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 2958
    Prev
    Next
    INDEX
    Explanations

    phrases related to political controversy

    oai_token-act-pair · gpt-3.5-turbo

    references to political activities and controversies involving Russia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Compass
    -0.73
    imet
    -0.72
     analyse
    -0.70
     ageing
    -0.69
     centres
    -0.67
     traveller
    -0.67
     learners
    -0.67
    ktop
    -0.67
     âĢº
    -0.66
    orient
    -0.66
    POSITIVE LOGITS
    shit
    0.89
     pissed
    0.84
     shit
    0.84
     goddamn
    0.84
     fucking
    0.83
     supposedly
    0.83
     botched
    0.83
     phony
    0.83
     thugs
    0.82
    HAHAHAHA
    0.81
    Activations Density 1.663%

    No Known Activations